@inproceedings{zhao-etal-2025-structuthink,
    title = "{S}tructu{T}hink: Reasoning with Task Transition Knowledge for Autonomous {LLM}-Based Agents",
    author = "Zhao, Haiyu  and
      Guo, Zhenyu  and
      Zhang, Chunhong  and
      Zhou, Ziyu  and
      Hu, Zheng",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1331/",
    doi = "10.18653/v1/2025.findings-emnlp.1331",
    pages = "24489--24506",
    ISBN = "979-8-89176-335-7",
    abstract = "Decision-making tasks have highlighted fundamental challenges in grounding decisions within real-world contexts. Traditional decision knowledge utilization methods often struggle to effectively integrate structured decision constraints, limiting their ability to decompose high-level tasks, maintain logical consistency, and adapt to dynamic environments. To bridge this gap, we introduce StructuThink, a knowledge-structured reasoning framework that enhances LLM-based agents with explicit decision constraints. Specifically, we propose the Task Transition Knowledge Graph (TTKG) that learning decision knowledge in embodied scenarios. Leveraging this knowledge, we propose the StructuThink framework, comprising a subtask chain constructor for grounding natural language instructions and a constraint-based executor for adaptive and consistent decision-making. We validate StructuThink across multiple benchmarks, including ALFWorld and WebShop, where it achieves higher task success rates (improving by up to 7{\%}) and more efficient action sequences (requiring up to 15{\%} fewer steps) than baseline methods. Our approach enables LLMs to more effectively ground decision-making in domain-specific scenarios, enhancing both interpretability and reliability, thus paving the way for more reliable and adaptable decision-making systems."
}